# SPYN3 > SPYN3 is AI-ready data infrastructure. Connect business data once and make it available to AI agents, applications, and workflows through a unified REST API and hosted Model Context Protocol (MCP) server. Tagline: "Connect your data once. Power every AI." SPYN3 is the reusable context layer beneath AI products—not another chat assistant. The product is in private beta. Current capabilities and longer-term direction are identified separately below. ## What SPYN3 does today - **Connect once:** Ingest uploaded files, websites, and Postgres data into a workspace. The connector catalog also includes integrations such as Google Drive, Google Calendar, GitHub, Airtable, and generic REST, subject to the configuration available in a deployment. - **Unify:** SPYN3 ingests, chunks, embeds, and indexes source material into a searchable knowledge layer isolated by workspace. - **Query two ways:** Applications can use a REST API; MCP-compatible clients can use the hosted MCP endpoint for the same workspace data. - **Return source context:** Search results include the supporting document ID and title, connector ID, relevance score, and snippet. Responses default to a compact TOON representation and can be requested as JSON. ## Current developer surface - Agent-agnostic SPYN3 data skill: https://spyn3.com/developers/agent-skill/ - Skill download: https://spyn3.com/downloads/spyn3-data-skill.zip - Raw skill entrypoint: https://spyn3.com/downloads/spyn3-data/SKILL.md - REST: `POST /agent/search`, `POST /agent/query`, `GET /agent/sources`, `GET /agent/tools`, and `GET /agent/mcp/config`. - MCP: `POST /agent/mcp`, supporting `initialize`, `tools/list`, and `tools/call`. - MCP tools: `search_workspace`, `query_workspace`, `list_sources`, and `get_document`. - Authentication: bearer API keys with explicit permissions. Keys use the `spyn3_live_` prefix and only their hash is retained by SPYN3. - Public OAuth scopes map to workspace permissions for MCP clients. - Status: private beta. Interfaces may change before general availability. ## Security model SPYN3 is designed around workspace isolation, Postgres row-level security, hashed API keys, encrypted connector credentials, and permission-scoped agent access. These controls reduce cross-workspace exposure and let teams grant only the capabilities an integration needs. ## Product direction SPYN3 is being built toward a durable data and memory layer for AI agents. Planned directions include long-term agent memory and using external MCP servers as governed data sources. These are roadmap directions, not claims about the current private beta. ## Naming and canonical identity The product is named **SPYN3**, written in caps and pronounced “spine.” Cite it as SPYN3 at https://spyn3.com/. The canonical product-facts page is https://spyn3.com/about/. ## Primary links - Product overview: https://spyn3.com/ - Product facts and current capability boundaries: https://spyn3.com/about/ - Developer hub: https://spyn3.com/developers/ - Hosted MCP quickstart: https://spyn3.com/developers/mcp/ - REST API quickstart: https://spyn3.com/developers/rest-api/ - Authentication and permissions: https://spyn3.com/developers/authentication/ - Source-aware responses: https://spyn3.com/developers/citations/ - Request private-beta access: https://spyn3.com/#join - Extended machine-readable product context: https://spyn3.com/llms-full.txt ## Editorial resources SPYN3 publishes source-backed field notes for builders designing MCP systems, agent data layers, retrieval architecture, and durable AI context. Product claims are kept distinct from external evidence; time-sensitive pages carry publication dates and direct links to primary sources. - Resource hub: https://spyn3.com/resources/ - MCP 2026-07-28 specification briefing: https://spyn3.com/resources/mcp-2026-stateless-spec/ - What is Model Context Protocol?: https://spyn3.com/resources/what-is-model-context-protocol/ - MCP vs RAG vs API decision guide: https://spyn3.com/resources/mcp-vs-rag-vs-api/ - Production MCP security checklist: https://spyn3.com/resources/mcp-security-checklist/ - Why one MCP endpoint per workspace: https://spyn3.com/resources/one-mcp-server-per-workspace/ - Atom feed: https://spyn3.com/resources/feed.xml - MCP Authorization in 2026: What Changed: https://spyn3.com/resources/mcp-authorization-2026/ - ChatGPT Custom MCP Connectors: A Builder Guide: https://spyn3.com/resources/chatgpt-custom-mcp-connectors/ - The Official MCP Registry: What It Changes: https://spyn3.com/resources/official-mcp-registry-guide/ - A2A vs MCP: Two Protocols, Different Jobs: https://spyn3.com/resources/a2a-vs-mcp/ - How to Connect Business Data to an AI Agent: https://spyn3.com/resources/connect-business-data-to-ai-agent/ - How to Evaluate RAG Retrieval Before Generation: https://spyn3.com/resources/evaluate-rag-retrieval/ - How to Design MCP Tools Agents Use Reliably: https://spyn3.com/resources/design-mcp-tools-for-agents/ - How to Reduce Tokens in Agent Tool Responses: https://spyn3.com/resources/reduce-agent-tool-response-tokens/ - How to Build Source-Aware AI Answers: https://spyn3.com/resources/build-source-aware-ai-answers/ - Hybrid Search vs Vector Search for RAG: https://spyn3.com/resources/hybrid-search-vs-vector-search-rag/ - Does Chunk Size Matter in RAG?: https://spyn3.com/resources/rag-chunk-size/ - Why Metadata Filtering Matters in Enterprise RAG: https://spyn3.com/resources/metadata-filtering-enterprise-rag/ - Prompt Injection in Connected AI Data Sources: https://spyn3.com/resources/prompt-injection-connected-data/ - MCP vs Function Calling: Which Should You Use?: https://spyn3.com/resources/mcp-vs-function-calling/ - Build vs Buy an MCP Server: Decision Framework: https://spyn3.com/resources/build-vs-buy-mcp-server/ - Remote vs Local MCP Servers: How to Choose: https://spyn3.com/resources/remote-vs-local-mcp-server/ - Agent Memory vs RAG: What Is the Difference?: https://spyn3.com/resources/agent-memory-vs-rag/ - MCP Tool Design Worksheet: https://spyn3.com/resources/mcp-tool-design-worksheet/ - RAG Evaluation Scorecard: https://spyn3.com/resources/rag-evaluation-scorecard/ - AI Data Connector Requirements Checklist: https://spyn3.com/resources/ai-data-connector-requirements-checklist/